Fully Kernected Neural Networks
In this paper, we apply kernel methods to deep convolutional neural network (DCNN) to improve its nonlinear ability. DCNNs have achieved significant improvement in many computer vision tasks. For an image classification task, the accuracy comes to saturation when the depth and width of network are e...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-01-01
|
| Series: | Journal of Mathematics |
| Online Access: | http://dx.doi.org/10.1155/2023/1539436 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832547943248297984 |
|---|---|
| author | Wei Zhang Zhi Han Xiai Chen Baichen Liu Huidi Jia Yandong Tang |
| author_facet | Wei Zhang Zhi Han Xiai Chen Baichen Liu Huidi Jia Yandong Tang |
| author_sort | Wei Zhang |
| collection | DOAJ |
| description | In this paper, we apply kernel methods to deep convolutional neural network (DCNN) to improve its nonlinear ability. DCNNs have achieved significant improvement in many computer vision tasks. For an image classification task, the accuracy comes to saturation when the depth and width of network are enough and appropriate. The saturation accuracy will not rise even by increasing the depth and width. We find that improving nonlinear ability of DCNNs can break through the saturation accuracy. In a DCNN, the former layer is more inclined to extract features and the latter layer is more inclined to classify features. Therefore, we apply kernel methods at the last fully connected layer to implicitly map features to a higher-dimensional space to improve nonlinear ability so that the network achieves better linear separability. Also, we name the network as fully kernected neural networks (fully connected neural networks with kernel methods). Our experiment result shows that fully kernected neural networks achieve higher classification accuracy and faster convergence rate than baseline networks. |
| format | Article |
| id | doaj-art-ba9db2912cc342ce8e2c075d3b478ac5 |
| institution | Kabale University |
| issn | 2314-4785 |
| language | English |
| publishDate | 2023-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Mathematics |
| spelling | doaj-art-ba9db2912cc342ce8e2c075d3b478ac52025-02-03T06:42:55ZengWileyJournal of Mathematics2314-47852023-01-01202310.1155/2023/1539436Fully Kernected Neural NetworksWei Zhang0Zhi Han1Xiai Chen2Baichen Liu3Huidi Jia4Yandong Tang5State Key Laboratory of RoboticsState Key Laboratory of RoboticsState Key Laboratory of RoboticsState Key Laboratory of RoboticsState Key Laboratory of RoboticsState Key Laboratory of RoboticsIn this paper, we apply kernel methods to deep convolutional neural network (DCNN) to improve its nonlinear ability. DCNNs have achieved significant improvement in many computer vision tasks. For an image classification task, the accuracy comes to saturation when the depth and width of network are enough and appropriate. The saturation accuracy will not rise even by increasing the depth and width. We find that improving nonlinear ability of DCNNs can break through the saturation accuracy. In a DCNN, the former layer is more inclined to extract features and the latter layer is more inclined to classify features. Therefore, we apply kernel methods at the last fully connected layer to implicitly map features to a higher-dimensional space to improve nonlinear ability so that the network achieves better linear separability. Also, we name the network as fully kernected neural networks (fully connected neural networks with kernel methods). Our experiment result shows that fully kernected neural networks achieve higher classification accuracy and faster convergence rate than baseline networks.http://dx.doi.org/10.1155/2023/1539436 |
| spellingShingle | Wei Zhang Zhi Han Xiai Chen Baichen Liu Huidi Jia Yandong Tang Fully Kernected Neural Networks Journal of Mathematics |
| title | Fully Kernected Neural Networks |
| title_full | Fully Kernected Neural Networks |
| title_fullStr | Fully Kernected Neural Networks |
| title_full_unstemmed | Fully Kernected Neural Networks |
| title_short | Fully Kernected Neural Networks |
| title_sort | fully kernected neural networks |
| url | http://dx.doi.org/10.1155/2023/1539436 |
| work_keys_str_mv | AT weizhang fullykernectedneuralnetworks AT zhihan fullykernectedneuralnetworks AT xiaichen fullykernectedneuralnetworks AT baichenliu fullykernectedneuralnetworks AT huidijia fullykernectedneuralnetworks AT yandongtang fullykernectedneuralnetworks |